Subverting Fair Image Search with Generative Adversarial Perturbations-Reference-Cited by-同舟云学术

Subverting Fair Image Search with Generative Adversarial Perturbations

Published:2022-06-20 Issue: Volume: Page:
ISSN:
Container-title:2022 ACM Conference on Fairness, Accountability, and Transparency
language:
Short-container-title:

Author:

Ghosh Avijit¹,Jagielski Matthew²,Wilson Christo¹

Affiliation:

1. Khoury College of Computer Sciences, Northeastern University, USA

2. Google Brain, USA

Funder

NSF (National Science Foundation)

Sloan Foundation

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3531146.3533128

Reference101 articles.

1. 116th Congress (2019-2020) . [n.d.]. H.R.2231 - Algorithmic Accountability Act of 2019 . https://www.congress.gov/bill/116th-congress/house-bill/2231. 116th Congress (2019-2020). [n.d.]. H.R.2231 - Algorithmic Accountability Act of 2019. https://www.congress.gov/bill/116th-congress/house-bill/2231.

2. Dzifa Adjaye-Gbewonyo Robert A Bednarczyk Robert L Davis and Saad B Omer. 2014. Using the Bayesian Improved Surname Geocoding Method (BISG) to create a working classification of race and ethnicity in a diverse managed care population: a validation study. Health services research 49 1 (2014) 268–283. Dzifa Adjaye-Gbewonyo Robert A Bednarczyk Robert L Davis and Saad B Omer. 2014. Using the Bayesian Improved Surname Geocoding Method (BISG) to create a working classification of race and ethnicity in a diverse managed care population: a validation study. Health services research 49 1 (2014) 268–283.

3. Alekh Agarwal Miroslav Dudík and Zhiwei Steven Wu. 2019. Fair regression: Quantitative definitions and reduction-based algorithms. arXiv preprint arXiv:1905.12843(2019). Alekh Agarwal Miroslav Dudík and Zhiwei Steven Wu. 2019. Fair regression: Quantitative definitions and reduction-based algorithms. arXiv preprint arXiv:1905.12843(2019).

4. Facebook AI. 2021. How we’re using Fairness Flow to help build AI that works better for everyone. Facebook AI. https://ai.facebook.com/blog/how-were-using-fairness-flow-to-help-build-ai-that-works-better-for-everyone/. Facebook AI. 2021. How we’re using Fairness Flow to help build AI that works better for everyone. Facebook AI. https://ai.facebook.com/blog/how-were-using-fairness-flow-to-help-build-ai-that-works-better-for-everyone/.

5. Defense Against Universal Adversarial Perturbations

Cited by 5 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Beyond Behaviorist Representational Harms: A Plan for Measurement and Mitigation;The 2024 ACM Conference on Fairness, Accountability, and Transparency;2024-06-03

2. Dsap: Analyzing Bias Through Demographic Comparison of Datasets;2024

3. Measuring Equality in Machine Learning Security Defenses: A Case Study in Speech Recognition;Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security;2023-11-26

4. When Fair Classification Meets Noisy Protected Attributes;Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society;2023-08-08

5. Inferring User Image-Search Goals Using SVM and Re-ranking process;2023 International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE);2023-01-27